Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    various forms of the verb "to be" and its related grammatical constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Vidite
    -0.58
     ་་
    -0.58
    IContainer
    -0.58
    protoimpl
    -0.57
     GIP
    -0.56
    Demografie
    -0.55
    ⓧ
    -0.55
    الدراسه
    -0.54
     entanto
    -0.53
    ContentAsync
    -0.53
    POSITIVE LOGITS
     comprised
    1.13
     a
    1.12
     the
    1.04
     called
    1.03
     located
    1.03
     considered
    1.01
     meant
    0.98
     represented
    0.93
     taken
    0.91
     an
    0.90
    Act Density 0.712%

    No Known Activations